(Press-News.org) A new system could tell you how likely it is for you to become ill if you visit a particular restaurant by 'listening' to the tweets from other restaurant patrons.
The University of Rochester researchers say their system, nEmesis, can help people make more informed decisions, and it also has the potential to complement traditional public health methods for monitoring food safety, such as restaurant inspections. For example, it could enable what they call "adaptive inspections," inspections guided in part by the real-time information that nEmesis provides.
The system combines machine-learning and crowdsourcing techniques to analyze millions of tweets to find people reporting food poisoning symptoms following a restaurant visit. This volume of tweets would be impossible to analyze manually, the researchers note. Over a four-month period, the system collected 3.8 million tweets from more than 94,000 unique users in New York City, traced 23,000 restaurant visitors, and found 480 reports of likely food poisoning. They also found they correlate fairly well with public inspection data by the local health department, as the researchers describe in a paper to be presented at the Conference on Human Computation & Crowdsourcing in Palm Springs, Calif., in November.
The system ranks restaurants according to how likely it is for someone to become ill after visiting that restaurant.
"The Twitter reports are not an exact indicator – any individual case could well be due to factors unrelated to the restaurant meal – but in aggregate the numbers are revealing," said Henry Kautz, chair of the computer science department at the University of Rochester and co-author of the paper. In other words, a "seemingly random collection of online rants becomes an actionable alert," according to Kautz, which can help detect cases of foodborne illness in a timely manner.
nEmesis "listens" to relevant public tweets and detects restaurant visits by matching up where a person tweets from and the known locations of restaurants. People will often tweet from their phones or other mobile devices, which are GPS enabled. This means that tweets can be "geotagged": the tweet not only provides information in the 140 characters allowed, but also about where the user was at the time.
If a user tweets from a location that is determined to be a restaurant (by using the locations of 24,904 restaurants that had been visited by the Department of Health and Mental Hygiene in New York City), the system will continue to track this person's tweets for 72 hours, even when they're not geotagged, or when they are tweeted from a different device. If a user then tweets about feeling ill, the system captures the information that this person is now ill and had visited a specific restaurant.
The correlation between the Twitter data and the public inspection data means that about one third of the inspection scores could be reliably predicted from the Twitter data. The remainder of the scores show some disagreement. "This disagreement is interesting as the public inspection data is not perfect either," argued co-author Adam Sadilek, formerly a colleague of Kautz at Rochester and who is now at Google. "The adaptive inspections could reveal the real risk, which is currently hidden for both methods."
This work builds on earlier work by Kautz and Sadilek that used Twitter to find out how likely a specific user was to have flu-like symptoms, and also to find the influence of different lifestyle factors on health. At the heart of all this work is the algorithm that Sadilek developed to distinguish between tweets that suggest a person tweeting is sick and those that don't. This algorithm is based on machine-learning, or as Sadilek described it, "it's like teaching a baby a new language," only in this case it's a computational algorithm that is being taught.
In their new system, nEmesis, they brought in an extra layer of complexity to improve the algorithm; they used crowdsourcing. For any one person, it would be exhausting and time-consuming to look through thousands of tweets to categorize them. The end results might not even be very accurate if their judgment is not quite right.
Instead the researchers turned to Amazon's Mechanical Turk system to reach out to a crowd of readily available workers. These were paid small amounts of money to categorize some tweets that could then be used to train the algorithm. They ensured the pool of tweets they were going use was of high accuracy by having more than one worker look at each tweet and incentivizing the right answer by paying the workers when their answer agreed with that of the majority and deducting money when it didn't. The algorithm was then able to learn from the training samples how to spot tweets that show people that are likely to have foodborne illnesses.
Of course, the system only considers people who tweet, who might not even be a representative sample of the whole population or of the population visiting a restaurant. But the Twitter data can be used together with knowledge gained from other sources to detect foodborne illness in a timely manner. It provides an extra layer – a passive level of monitoring – which is cost-effective. And the information that nEmesis offers can benefit both Twitter and non-Twitter users.
Rochester researchers Sean Brennan, graduate student, and Vincent Silenzio, associate professor of psychiatry, are also both part of the team that worked on nEmesis.
INFORMATION:
The University of Rochester is one of the nation's leading private universities. Located in Rochester, N.Y., the University gives students exceptional opportunities for interdisciplinary study and close collaboration with faculty through its unique cluster-based curriculum. Its College, School of Arts and Sciences, and Hajim School of Engineering and Applied Sciences are complemented by its Eastman School of Music, Simon School of Business, Warner School of Education, Laboratory for Laser Energetics, School of Medicine and Dentistry, School of Nursing, Eastman Institute for Oral Health, and the Memorial Art Gallery.
Tracking Twitter may enhance monitoring of food safety at restaurants
2013-08-07
ELSE PRESS RELEASES FROM THIS DATE:
CD4 count is non-inferior to viral load for treatment switching in adults with HIV
2013-08-07
For adults infected with HIV in Thailand a monitoring strategy based on CD4 count (a type of white blood cell) is non-inferior to the recommended monitoring strategy measuring the amount of HIV virus in a patient's blood, to determine when to switch from first-line to more costly second-line antiretroviral treatment according to a clinical trial published this week in PLOS Medicine.
The study was conducted by an international team of researchers led by Marc Lallemant from Chiang Mai University, Thailand and the Harvard School of Public Health, United States and provides ...
Scientists discover Par-1 as a new component of the Hippo signaling pathway
2013-08-07
In the development of animals, which is closely controlled by diverse pathways, the regulation of organ size has been a long-standing puzzle. How does an organ ascertain its optimum size? What are the molecular mechanisms that stop organ growth at an appropriate point during development or regeneration? Almost a decade ago, the discovery of the Hippo signaling pathway provided an important starting point for answering these questions.
Now, a team of scientists led by Lei Zhang at the Shanghai Institute of Biochemistry & Cell Biology, Chinese Academy of Sciences, has ...
Treating PTSD and alcohol abuse together doesn't increase drinking, Penn study finds
2013-08-07
PHILADELPHIA— Contrary to past concerns, using prolonged exposure therapy to treat patients with post-traumatic stress disorder (PTSD) and comorbid alcohol dependence does not increase drinking or cravings, Penn Medicine psychiatrists report in the August 7 issue of JAMA, a theme issue on violence/human rights. In a first-of-its-kind single-blind, randomized clinical trial, researchers also found that PTSD patients treated with naltrexone for alcohol dependence drank less—and that the use of prolonged exposure therapy and naltrexone better protects PTSD patients from ...
Medfly and other fruit flies entrenched in California, study concludes
2013-08-07
Research to be published Aug. 7 in the highly respected international journal Proceedings of the Royal Society B clearly demonstrates that at least five and as many as nine species of tropical fruit flies, including the infamous Medfly, are permanently established in California and inexorably spreading, despite more than 30 years of intervention and nearly 300 state-sponsored eradication programs aimed at the flies.
The new study by a trio of scientists affiliated with the University of California, Davis, has significant implications for how government agencies develop ...
Study identifies factors associated with suicide risk among military personnel
2013-08-07
In an examination of risk factors associated with suicide in current and former military personnel observed 2001 and 2008, male sex and mental disorders were independently associated with suicide risk but not military-specific variables, findings that do not support an association between deployment or combat with suicide, according to a study in the August 7 issue of JAMA, a theme issue on violence/human rights.
"Despite universal access to healthcare services, mandatory suicide prevention training, and other preventive efforts, suicide has become one of the leading ...
Treatment for PTSD and risk of drinking among individuals with alcohol dependence
2013-08-07
In a trial that included patients with alcohol dependence and posttraumatic stress disorder (PTSD), treatment with the drug naltrexone resulted in a decrease in the percentage of days drinking while use of the PTSD treatment, prolonged exposure therapy, was not associated with increased drinking or alcohol craving, according to a study in the August 7 issue of JAMA, a theme issue on violence/human rights.
"Alcohol dependence and PTSD are highly comorbid [co-existing], yet little is known about how best to treat this large, highly dysfunctional, and distressed population. ...
Identifying need, providing delivery of mental health services following community disasters
2013-08-07
A review of articles on disaster and emergency mental health response interventions and services indicates that in postdisaster settings, a systematic framework of case identification, triage, and mental health interventions should be integrated into emergency medicine and trauma care responses, according to a study in the August 7 issue of JAMA, a theme issue on violence/human rights.
"Mental and physical consequences of major disasters have garnered increasing attention to the need for an effective community response. It is estimated that much of the U.S. population ...
Number of scientific publications on firearms shows modest increase in recent years
2013-08-07
"In January 1996, Congress passed an appropriations bill amendment prohibiting the U.S. Centers for Disease Control and Prevention (CDC) from using 'funds made available for injury prevention ... to advocate or promote gun control.' This provision was triggered by evidence linking gun ownership to health harms, created uncertainty among CDC officials and researchers about what could be studied, and led to significant declines in funding," write Joseph A. Ladapo, M.D., Ph.D., of the New York University School of Medicine, New York, and colleagues.
As reported in a Research ...
Dolphins keep lifelong social memories, longest in a non-human species
2013-08-07
Dolphins can recognize their old tank mates' whistles after being separated for more than 20 years — the longest social memory ever recorded for a non-human species.
The remarkable memory feat is another indication that dolphins have a level of cognitive sophistication comparable to only a few other species, including humans, chimpanzees and elephants. Dolphins' talent for social recognition may be even more long-lasting than facial recognition among humans, since human faces change over time but the signature whistle that identifies a dolphin remains stable over many ...
Researchers uncover brain molecule regulating human emotion, mood
2013-08-07
A RIKEN research team has discovered an enzyme called Rines that regulates MAO-A, a major brain protein controlling emotion and mood. The enzyme is a potentially promising drug target for treating diseases associated with emotions such as depression.
Monoamine oxidase A (MAO-A) is an enzyme that breaks down serotonin, norephinephrine and dopamine, neurotransmitters well-known for their influence on emotion and mood. Nicknamed the "warrior gene", a variant of the MAOA gene has been associated with increased risk of violent and anti-social behavior.
While evidence points ...